3 accepted papers
The spatial information inherent in 3D point clouds is crucial for robotic manipulation. However, existing 3D pre-training methods face a fundamental trade-off: Masked Autoencoding (MAE) excels at capturing spatial-geometric features but lacks semantics, whereas contrastive learning, while able to d…
Accurate spatial-geometric perception remains fundamental to robotic grasping, yet physical artifacts in real depth maps like voids and noise establish a significant sim-to-real gap that critically impedes policy transfer. Training-time strategies like procedural noise injection or learned mappings …
Effectively manipulating articulated objects in household scenarios is a crucial step toward achieving general embodied artificial intelligence. Mainstream research in 3D vision has primarily focused on manipulation through depth perception and pose detection. However, in real-world environments, th